Commit 82490058 authored by Jonas Schüppen's avatar Jonas Schüppen
Browse files

Added some more postprocessing functions

parent 9c968275

generateBaseline/postprocessing.py

+43 −1
Original line number Diff line number Diff line
@@ -16,6 +16,9 @@ from docx.oxml import OxmlElement 
from docx.oxml.ns import qn

from docx.shared import Cm



from postprocessing_styling import postprocess_etsi_styles





def parse_input(args_to_parse=None, description = None):

    """

    args_to_parse: list of arguments, e.g. ["input", "output"]
@@ -117,6 +120,16 @@ def table_width_adjustment_cli(): 
                                                 description="Set the width of table columns according to values in json or if non there to be equal.")

    table_widths_adjustment(docx_input, docx_output, tables_folder)



def postprocess_etsi_styles_cli():

    docx_input, docx_output = parse_input(description="Update styles in document according to etsi styles (currently not ready, just a few styles).")

    postprocess_etsi_styles(docx_input, docx_output)



def remove_docx_metadata_cli():

    docx_input, docx_output = parse_input(

        description="Remove metadata from docx.")

    postprocess_etsi_styles(docx_input, docx_output)





def apply_standard_style_to_unformatted_paragraphs(docx_input, docx_output, standard_style_name = "Normal"):

    # Filter warning

    warnings.filterwarnings(
@@ -486,3 +499,32 @@ def table_widths_adjustment(docx_input, docx_output, tables_folder): 
                cell = row.cells[i]

                cell.width = width

    doc.save(docx_output)



def remove_docx_metadata(docx_input, docx_output):

    """

    removes metadata from word file.

    """

    # 1. Eigenschaften mit python-docx leeren

    doc = Document(docx_input)

    props = doc.core_properties

    props.author = None

    props.last_modified_by = None

    props.title = None

    props.subject = None

    props.comments = None

    props.keywords = None

    props.category = None

    doc.save(docx_output)



    # 2. Metadaten-Dateien aus dem ZIP löschen

    tmp_path = docx_output + ".tmp"

    shutil.copy(docx_output, tmp_path)



    with zipfile.ZipFile(tmp_path, "r") as zin:

        with zipfile.ZipFile(docx_output, "w") as zout:

            for item in zin.infolist():

                if item.filename not in ["docProps/core.xml", "docProps/app.xml"]:

                    zout.writestr(item, zin.read(item))



    os.remove(tmp_path)

    print(f"Successfully removed metadata from {docx_input} and wrote it to {docx_output}")
 
 No newline at end of file

generateBaseline/postprocessing_styling.py

0 → 100644
+53 −0
Original line number Diff line number Diff line 
import re



from docx import Document

from docx.shared import Cm





def change_annex_heading_formats(doc):



    for para in doc.paragraphs:

        if para.style.name == "Heading 1":

            text = para.text.strip()

            if not text:

                continue



            first_word = text.split()[0]



            # Beispiel: Bedingte Formatänderung

            if first_word.lower().startswith("annex"):

                para.style = doc.styles['Heading 8']

    return doc



def intent_example_and_note(doc):

    for para in doc.paragraphs:

        if para.text.strip().startswith("NOTE") or para.text.strip().startswith("EXAMPLE"):



            if para.text.strip().startswith("NOTE"):

                # Einzug vergrößern

                para.paragraph_format.left_indent = Cm(2)

                # Hängender Einzug setzen

                para.paragraph_format.first_line_indent = Cm(-1.5)

            else:

                # Einzug vergrößern

                para.paragraph_format.left_indent = Cm(2.5)

                # Hängender Einzug setzen

                para.paragraph_format.first_line_indent = Cm(-2)



            # set Tab after ":"

            # Liste der Keywords

            keywords = ["EXAMPLE", "NOTE"]



            # Regex bauen: (EXAMPLE|NOTE)\s*\d* → Keyword optional mit Zahl

            pattern = re.compile(r'(' + '|'.join(keywords) + r'\s*\d*)\s*:\s*(.*)')



            para.text = pattern.sub(r'\1:\t\2', para.text)









def postprocess_etsi_styles(docx_input, docx_output):

    doc = Document(docx_input)

    change_annex_heading_formats(doc)

    intent_example_and_note(doc)

    doc.save(docx_output)
 
 No newline at end of file

generateBaseline/setup.py

+2 −0
Original line number Diff line number Diff line
@@ -22,6 +22,8 @@ setup( 
        						#"apply_etsi_styling: postprocessing:postprocess_etsi_styles",

        						"update_toc=postprocessing:update_toc_cli",

								"refresh_docx_fields=postprocessing:refresh_docx_fields_cli",

                                "apply_etsi_styling=postprocessing:postprocess_etsi_styles_cli",

                                "remove_metadata=postprocessing:remove_docx_metadata_cli"

			]

            }